Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 556 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 4.9767. Min Range: -4.9767

Max Act: 4.9767. Min Act: -0.1700

Data Index: 7109362 (Open Web Text)

Max Activating Token Index: 175

Text #1

Max Range: 4.9767. Min Range: -4.9767

Max Act: 4.9683. Min Act: -0.1700

Data Index: 4108987 (Open Web Text)

Max Activating Token Index: 732

Text #2

Max Range: 4.9767. Min Range: -4.9767

Max Act: 4.9721. Min Act: -0.1700

Data Index: 3233676 (Open Web Text)

Max Activating Token Index: 542

Text #3

Max Range: 4.9767. Min Range: -4.9767

Max Act: 4.9603. Min Act: -0.1700

Data Index: 5743077 (Open Web Text)

Max Activating Token Index: 24

Text #4

Max Range: 4.9767. Min Range: -4.9767

Max Act: 4.9521. Min Act: -0.1700

Data Index: 3678145 (Open Web Text)

Max Activating Token Index: 412

Text #5

Max Range: 4.9767. Min Range: -4.9767

Max Act: 4.9347. Min Act: -0.1700

Data Index: 6957331 (Open Web Text)

Max Activating Token Index: 599

Text #6

Max Range: 4.9767. Min Range: -4.9767

Max Act: 4.9231. Min Act: -0.1699

Data Index: 758522 (Open Web Text)

Max Activating Token Index: 430

Text #7

Max Range: 4.9767. Min Range: -4.9767

Max Act: 4.8886. Min Act: -0.1700

Data Index: 1522985 (Open Web Text)

Max Activating Token Index: 147

Text #8

Max Range: 4.9767. Min Range: -4.9767

Max Act: 4.8995. Min Act: -0.1700

Data Index: 8697735 (Open Web Text)

Max Activating Token Index: 508

Text #9

Max Range: 4.9767. Min Range: -4.9767

Max Act: 4.8951. Min Act: -0.1700

Data Index: 7292938 (Open Web Text)

Max Activating Token Index: 69

Text #10

Max Range: 4.9767. Min Range: -4.9767

Max Act: 4.8964. Min Act: -0.1700

Data Index: 601228 (Open Web Text)

Max Activating Token Index: 41

Text #11

Max Range: 4.9767. Min Range: -4.9767

Max Act: 4.8915. Min Act: -0.1700

Data Index: 2000398 (Open Web Text)

Max Activating Token Index: 431

Text #12

Max Range: 4.9767. Min Range: -4.9767

Max Act: 4.9299. Min Act: -0.1700

Data Index: 3710796 (Open Web Text)

Max Activating Token Index: 964

Text #13

Max Range: 4.9767. Min Range: -4.9767

Max Act: 4.9100. Min Act: -0.1700

Data Index: 2774838 (Open Web Text)

Max Activating Token Index: 1015

Text #14

Max Range: 4.9767. Min Range: -4.9767

Max Act: 4.8971. Min Act: -0.1700

Data Index: 9115 (Open Web Text)

Max Activating Token Index: 500

Text #15

Max Range: 4.9767. Min Range: -4.9767

Max Act: 4.9045. Min Act: -0.1700

Data Index: 3627627 (Open Web Text)

Max Activating Token Index: 983

Text #16

Max Range: 4.9767. Min Range: -4.9767

Max Act: 4.8776. Min Act: -0.1700

Data Index: 2532097 (Open Web Text)

Max Activating Token Index: 808

Text #17

Max Range: 4.9767. Min Range: -4.9767

Max Act: 4.8765. Min Act: -0.1700

Data Index: 3315002 (Open Web Text)

Max Activating Token Index: 462

Text #18

Max Range: 4.9767. Min Range: -4.9767

Max Act: 4.8920. Min Act: -0.1700

Data Index: 2062922 (Open Web Text)

Max Activating Token Index: 490

Text #19

Max Range: 4.9767. Min Range: -4.9767

Max Act: 4.8575. Min Act: -0.1700

Data Index: 3327713 (Open Web Text)

Max Activating Token Index: 430